© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24809
    Prev
    Next
    INDEX
    Explanations

    non-English negation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     indem
    0.38
    櫳
    0.37
     lés
    0.36
    祜
    0.36
    اث
    0.36
    눔
    0.36
     oon
    0.35
     thinking
    0.34
    ील
    0.34
    리지
    0.34
    POSITIVE LOGITS
     안
    1.80
    안
    1.47
    安
    1.28
     安
    1.10
     ما
    0.92
     Ан
    0.85
     مَا
    0.83
     An
    0.81
    <0x8E>
    0.80
    An
    0.78
    Activations Density 0.000%

    No Known Activations